Claim Missing Document
Check
Articles

Found 28 Documents
Search

PARAMETER ESTIMATION OF COVID-19 COMPARTMENT MODEL IN INDONESIA USING PARTICLE SWARM OPTIMIZATION Raqqasyi Rahmatullah Musafir; Syaiful Anam
Jurnal Berkala Epidemiologi Vol. 10 No. 3 (2022): Jurnal Berkala Epidemiologi (Periodic Epidemiology Journal)
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jbe.V10I32022.283-292

Abstract

Background: The government established a vaccination program to deal with highly reactive COVID-19 cases in Indonesia. In obtaining accurate predictions of the dynamics of the compartment model of COVID-19 spread, a good parameter estimation technique was required.. Purpose: This research aims to apply Particle Swarm Optimization as a parameter estimation method to obtain parameters value from the Susceptible-Vaccinated-Infected-Recovered compartment model of COVID-19 cases. Methods: This research was conducted in April-May 2020 in Indonesia with exploratory design research.  The researchers used the data on COVID-19 cases in Indonesia, which was accessed at covid19.go.id. The data set contained the number of reactive cases, vaccinated cases, and recovered cases. The data set was used to estimate the parameters of the COVID-19 compartment model. The results were shown by numerical simulations that apply to the Matlab program. Results: Research shows that the parameters estimated using Particle Swarm Optimization have a fairly good value because the mean square error is relatively small compared to the data size used. Reactive cases of COVID-19 have decreased until August 21, 2021. Next, reactive cases of COVID-19 will increase until the end of 2021. It is because the virus infection rate of the vaccinated population is positive . If  occurs before the stationary point, then the reactive cases of COVID-19 will decrease mathematically. Conclusion: Particle Swarm Optimization methods can estimate parameters well based on mean square error and the graphs that can describe the behavior of COVID-19 cases in the future.
Pelatihan Pembelajaran Matematika Menggunakan Perangkat Lunak Matematika bagi Guru–Guru Matematika SMA/MA di Kabupaten Pasuruan Syaiful Anam; Agus Widodo; Indah Yanti; Corina Karim; Fery Widhiatmoko; Mochamad Hakim Akbar Assidiq Maulana
COMSERVA : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 2 No. 7 (2022): COMSERVA : Jurnal Penelitian dan Pengabdian Masyarakat
Publisher : Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59141/comserva.v2i7.422

Abstract

Pasuruan Regency has natural resources that have the potential to be developed, especially in the fields of agriculture, plantations and tourism. In an effort to improve the quality of human resources, improving the level of education is an important thing to do. One way to increase the number of people's participation in education is to improve the quality of learning so that people are interested in taking higher education levels. Learning media with mathematics software is expected to be able to visualize abstract mathematical objects so that it can improve students' understanding and encourage student learning motivation. GeoGebra is a mathematical software to visualize abstract mathematical objects quickly and accurately and can be used as a tool to construct mathematical concepts. One of the objectives of this activity is to improve the ability and skills of mathematics teachers in SMA/MA in Pasuruan Regency in developing mathematics learning media with GeoGebra software to visualize abstract mathematical objects (geometry objects). In addition, to improve the ability and skills of mathematics teachers in SMA/MA in Pasuruan Regency in explaining mathematical material containing geometric objects by utilizing Geogebra. The results of the training showed that the ability and skills of SMA/MA teachers in Pasuruan Regency increased significantly in the development of teaching media and in explaining geometric objects by using Geogebra.
Prediksi Jumlah Penderita COVID-19 di Kota Malang Menggunakan Jaringan Syaraf Tiruan Backpropagation dan Metode Conjugate Gradient Syaiful Anam; Mochamad Hakim Akbar Assidiq Maulana; Noor Hidayat; Indah Yanti; Zuraidah Fitriah; Dwi Mifta Mahanani
Prosiding Seminar Nasional Teknoka Vol 5 (2020): Prosiding Seminar Nasional Teknoka ke - 5
Publisher : Fakultas Teknik, Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

COVID-19 is an infectious disease caused by infection with a new type of corona virus. This disease is very dangerous and causes death, especially for sufferers who have congenital diseases or who have low immunity. The disease is spread through droplets from the nose or mouth that come out when a person infected with COVID-19 coughs, sneezes or talks. The prediction of the number of COVID-19 sufferers is very important to prevent and combat the spread of this disease. The backpropagation neural network is a method that can be used to solve predictive problems with good results, but its performance is influenced by the optimization method used during training. In general, the optimization method used is the gradient descent method, but this method has slow convergence. The Conjugate Gradient method has very good convergence when compared to the gradient descent method. In this paper, we will discuss how to make a prediction model for the number of COVID-19 sufferers in Malang using the backpropagation neural network and the conjugate gradient method. The experimental results show that the prediction model gets good results when compared to artificial neural networks that are optimized by the gradient descent method.
The Artificial Bee Colony (ABC) Algorithm for Estimating Parameter of Epidemic Influenza Model Ririn Nirmalasari; Agus Suryanto; Syaiful Anam
The Journal of Experimental Life Science Vol. 10 No. 1 (2020)
Publisher : Postgraduate School, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1048.636 KB) | DOI: 10.21776/ub.jels.2019.010.01.06

Abstract

The Artificial Bee Colony (ABC) is one of the stochastic algorithms that can be applied to solve many real-world optimization problems. In this paper, The ABC algorithm was used to estimate the parameter of the epidemic influenza model. This model consists of a differential system represented by variations of Susceptible (S), Exposed (E), Recovered (R), and Infected (I). The ABC processes explore the minimum value of the mean square error function in the current iteration to estimate the unknown parameters of the model. Estimating parameters were made using participation data containing influenza disease in Australia, 2017. The best parameter chosen from the ABC process matched the dynamical behavior of the influenza epidemic field data used. Graphical analysis was used to validate the model. The result shows that the ABC algorithm is efficient for estimating the parameter of the epidemic influenza model. Keywords: ABC, Epidemic, Estimate, Influenza, Parameter.
Penerapan Metode Learning Vector Quantization (LVQ) untuk Klasifikasi Fungsi Senyawa Aktif Menggunakan Notasi Simplified Molecular Input Line System (SMILES) Suhhy Ramzini; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1367.811 KB)

Abstract

Active compound is a substance (medicine) capable of providing kind effect when the human bodies are in bad shape. Active compound often used for preventing or curing a disease. Active compound takes an important role in medical world. Simplified Molecular Input Line System notation, in short SMILES notation is representation of compound (carbon bond) created by David Weininger in 1980. SMILES notation composed of ASCII (American Standard Code for Information Interchange) characters so that it can be stored in string variable and easily processed by the computer. Currently, there are numbers of compounds (SMILES notation) and it makes the classification for tested compound that can be made into a medicine (active compound) becomes necessary. The purpose of this research is to classify the active compound function utilizing SMILES notation with Learning Vector Quantization (LVQ) method by using 2 active compound function classes, one for metabolic disease, and another for cancer disease. There are 467 datasets with each 11 features. On testing process, the obtained value for learning rate is 0.1, decrement alpha is 0.3, minimum alpha is , and maximum epoch is 15 by using a percentage of 80% training data and 20% testing data which produce accuracy of 76.34%.
Implementasi Fuzzy K-Nearest Neighbor (FK-NN) Untuk Mengklasifikasi Fungsi Senyawa Berdasarkan Simplified Molecular Input Line Entry System (SMILES) Raden Rizky Widdie Tigusti; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (297.598 KB)

Abstract

The active compound is a chemical compound that has many functions. One of the functions of the active compound is as a medicine. Active compounds have special characteristics that determine function as a drug. To obtain a characteristic value on the active compound SMILES notation are used as input system. SMILES notation is a modern chemical notation that can be stored on string variables to use for the process of computing. To obtain the characteristic on the compound the SMILES notation will be divided into 12 features consisting of B, C, N, O, P, S, F, Cl, Br, I, OH and the length from SMILES notation. The value of each feature is obtained from the preprocessing process against the SMILES notation made at the beginning of the classification process.In the process of classifying the function of active compounds, the Fuzzy K-Nearest Neighbor method are used because it can do process by using large amounts of data. The Fuzzy K-Nearest Neighbor method is a combination of two methods namely Fuzzy and K-Nearest Neighbor. An important step of the classification process using the Fuzzy K-Nearest Neighbor is to calculate the distance from each test data to the train data or so-called by euclidean distance, pick value as much as k value and calculate the fuzzy. Tests in this study using the dataset as much as 631 and divided into 2 as the data train and test data. Each composition of data training and data testing are 80% (503 data) and 20% (128 data). The result of the accuracy is 71% with the value of k = 15, in other test by using k-fold cross validation the biggest accuracy is 77%.
Pengelompokan Fungsi Aktif Senyawa Data SMILES (Simplified Molecular Input Line Entry System) Menggunakan Metode K-Means Dengan Inisialisasi Pusat Klaster Menggunakan Metode Heuristic O(N LogN) Sherly Witanto; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (932.274 KB)

Abstract

Active compounds have function as a medicine that can prevent or cure diseases. Some of the active compounds have been known the function and some are still in the research stage. Currently in Indonesia there is still no program that capable to classifying chemical compounds as drugs for certain diseases. SMILES notation is the conversion of chemical compounds in the form of line notation. Notation SMILES able to provide convenience to the process of computerization on the classification of chemical compounds. The classification of the SMILES notation is carried out by taking the values ​​of the B, S, N, O, I, F, C, P, Cl, Br and OH atoms present in the compound. Before being processed, to get the value of the feature is done by dividing the process of each atom with the length of the compound. K-Means algorithm is the most widely used clustering method because it is easy and simple. The grouping of active function using K-Means method has weakness in random cluster initialization process, so that heuristic method o (n logn) is used to get the cluster initials with better value. Based on the software that has been made, the test is done using 512 of training data and test data as much as 128. Accuracy obtained from the test that is equal to 63% and testing using ¬K-Fold Cross Validation with 10 times the test produces an average accuracy of 52,58 %. Testing using K-Means with heuristic o (n logn) yielded better accuracy compared to conventional K-Means.
Penerapan Algoritme C4.5 untuk Klasifikasi Fungsi Senyawa Aktif Menggunakan Kode Simplified Molecular Input Line System (SMILES) Mochammad Iskandar Ardiyansyah Rochman; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (771.802 KB)

Abstract

Compounds are things that are often found in this world, with a substance that is a collection of compounds (Educated, 2015). The compound itself is divided into active and inactive compounds. The compound has a function that may be utilized for some aspect if it has a function like a drug or a stimulating hormone work. notation of SMILES (Simplified Molecular Input Line System) by David Weininger in 1980. SMILES notation takes advantage of ASCII characters that are very easy to process by the computer. SMILES notation classification process will be very useful to know the function class of the compound. This study was conducted to classify the function of the compound utilizing the SMILES notation by applying the C4.5 algorithm while the object is 2 classes of compound function, including the class of cancer and metabolism. Features tested from research as many as 11 features. The results of the best tests when the discretization technique is performed using entropy based discretization techniques, dividing the SMILES notation values ​​on each feature attribute, and the use of practicable data as much as possible will result in an accuracy of 79.34%. While the accuracy of the cross validation test shows an accuracy of 70.18%.
Implementasi Gabungan Metode K-Means Learning Vector Quantization (LVQ) Untuk Klasifikasi Fungsi Senyawa Aktif Menggunakan Data SMILES Nur Khilmiyatul Ilmiyah; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (964.381 KB)

Abstract

The active compound is a chemical compound that has many functions. While the inactive compound, doesn't have much function only as additional substances. Active compounds can be divided into two therapeutic functions as alternative medicine, and Pharmacology function to control drug containing the active compounds in it. In order to get functions in the active compounds used notation SMILES. SMILES notation is a representation of the active compounds with modern chemical notation, so that the computer can read the elements of the compound. Of the many SMILES notations at this time, all the SMILES notations cannot be used as medicine because they are still in the testing phase. SMILES notation that has been tested could be used as medicine. Therefore, this research will be built a fixed classification model that takes into account all the data. Based on the test results, the K-Means method of combined Learning Vector Quantization (LVQ) generate value accuracy of 72.22%, K-means conventional 52.65%, while Learning Vector Quantization (LVQ) owns 67.96%. The results show that the combined K-Means method of Learning Vector Quantization (LVQ) have better results than conventional K-means and Learning Vector Quantization (LVQ).
Momentum Backpropagation Untuk Klasifikasi Fungsi Senyawa Aktif Berdasarkan Notasi SMILES (Simplified Molecular Input Line Entry System) Nyimas Ayu Widi Indriana; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (764.799 KB)

Abstract

Active compounds can be used to make certain drugs and very important in the medical sector. Classification of active compounds is the most important thing in making medicines. After classifying the active compound, it is continued with the process of making and testing drugs that require a variety of tools. The cost of making and testing these drugs requires a high cost and time. This is a major obstacle for medical experts to make certain medicines. By utilizing current technology, a system can be made to classification process of active compounds, so the performance of medical experts for making certain drugs can be faster. The classification process can be done by using a computer and utilizing the SMILES notation. SMILES notation allows a compound to be processed by a computer. The momentum Backpropagation method can be used to perform the classification process properly. Based on the program that has been made, there are 4 types of testing using 522 training data and 131 test data producing, the best accuracy of 70,99% with a learning rate of 0,00001, max epoch of 100, momentum of 0,25 and hidden layer neurons of 4.